File size: 1,806 Bytes
57e3831 9f4b1c6 57e3831 9f4b1c6 57e3831 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 |
import gradio as gr
# Function to handle model inference with config
def generate_text(prompt, temperature, max_tokens):
# Simulate model inference with config (replace with actual model call)
response = f"Response to '{prompt}' with temperature={temperature} and max_tokens={max_tokens}"
return response
# Gradio interface
with gr.Blocks() as demo:
with gr.Sidebar():
gr.Markdown("# Inference Provider")
gr.Markdown("This Space showcases the deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct model, served by the nebius API. Sign in with your Hugging Face account to use this API.")
token_input = gr.Textbox(label="Hugging Face Token", type="password")
login_button = gr.Button("Sign in")
login_status = gr.Markdown("")
# Model configuration
gr.Markdown("### Model Configuration")
temperature = gr.Slider(0.1, 1.0, value=0.7, label="Temperature")
max_tokens = gr.Slider(10, 500, value=100, label="Max Tokens")
# Input and output components
with gr.Column():
prompt = gr.Textbox(label="Your Prompt")
output = gr.Textbox(label="Model Response")
generate_button = gr.Button("Generate")
# Load the model
model_interface = gr.load("models/deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct", provider="nebius")
# Handle login (example logic)
def handle_login(token):
if token: # Replace with actual authentication logic
return "Logged in successfully!"
else:
return "Please enter a valid token."
# Handle text generation
generate_button.click(generate_text, [prompt, temperature, max_tokens], output)
# Handle login
login_button.click(handle_login, inputs=token_input, outputs=login_status)
# Launch the app
demo.launch() |